Autonomous visual navigation is an essential element in robot autonomy. Reinforcement learning (RL) offers a promising policy training paradigm. However existing RL methods suffer from high sample complexity, poor sim-to-real transfer, and limited runtime adaptability to navigation scenarios not seen during training. These problems are particularly challenging for drones, with complex nonlinear and unstable dynamics, and strong dynamic coupling between control and perception. In this paper, we propose a novel framework that integrates 3D Gaussian Splatting (3DGS) with differentiable deep reinforcement learning (DDRL) to train vision-based drone navigation policies. By leveraging high-fidelity 3D scene representations and differentiable simulation, our method improves sample efficiency and sim-to-real transfer. Additionally, we incorporate a Context-aided Estimator Network (CENet) to adapt to environmental variations at runtime. Moreover, by curriculum training in a mixture of different surrounding environments, we achieve in-task generalization, the ability to solve new instances of a task not seen during training. Drone hardware experiments demonstrate our method's high training efficiency compared to state-of-the-art RL methods, zero shot sim-to-real transfer for real robot deployment without fine tuning, and ability to adapt to new instances within the same task class (e.g. to fly through a gate at different locations with different distractors in the environment).

3D Gaussian Splatting offers expressive scene reconstruction, modeling a broad range of visual, geometric, and semantic information. However, efficient real-time map reconstruction with data streamed from multiple robots and devices remains a challenge. To that end, we propose HAMMER, a server-based collaborative Gaussian Splatting method that leverages widely available ROS communication infrastructure to generate 3D, metric-semantic maps from asynchronous robot data-streams with no prior knowledge of initial robot positions and varying on-device pose estimators. HAMMER consists of (i) a frame alignment module that transforms local SLAM poses and image data into a global frame and requires no prior relative pose knowledge, and (ii) an online module for training semantic 3DGS maps from streaming data. HAMMER handles mixed perception modes, adjusts automatically for variations in image pre-processing among different devices, and distills CLIP semantic codes into the 3D scene for open-vocabulary language queries. In our real-world experiments, HAMMER creates higher-fidelity maps (2x) compared to competing baselines and is useful for downstream tasks, such as semantic goal-conditioned navigation (e.g., ``go to the couch"). Accompanying content available at hammer-project.github.io.

We present Splat-MOVER, a modular robotics stack for open-vocabulary robotic manipulation, which leverages the editability of Gaussian Splatting (GSplat) scene representations to enable multi-stage manipulation tasks. Splat-MOVER consists of: (i) ASK-Splat, a GSplat representation that distills semantic and grasp affordance features into the 3D scene. ASK-Splat enables geometric, semantic, and affordance understanding of 3D scenes, which is critical in many robotics tasks; (ii) SEE-Splat, a real-time scene-editing module using 3D semantic masking and infilling to visualize the motions of objects that result from robot interactions in the real-world. SEE-Splat creates a "digital twin" of the evolving environment throughout the manipulation task; and (iii) Grasp-Splat, a grasp generation module that uses ASK-Splat and SEE-Splat to propose affordance-aligned candidate grasps for open-world objects. ASK-Splat is trained in real-time from RGB images in a brief scanning phase prior to operation, while SEE-Splat and Grasp-Splat run in real-time during operation. We demonstrate the superior performance of Splat-MOVER in hardware experiments on a Kinova robot compared to two recent baselines in four single-stage, open-vocabulary manipulation tasks and in four multi-stage manipulation tasks, using the edited scene to reflect changes due to prior manipulation stages, which is not possible with existing baselines. The project page is available at https://splatmover.github.io, and the code for the project will be made available after review.

We present Splat-Nav, a real-time navigation pipeline designed to work with environment representations generated by Gaussian Splatting (GSplat), a popular emerging 3D scene representation from computer vision. Splat-Nav consists of two components: 1) Splat-Plan, a safe planning module, and 2) Splat-Loc, a robust pose estimation module. Splat-Plan builds a safe-by-construction polytope corridor through the map based on mathematically rigorous collision constraints and then constructs a B\'ezier curve trajectory through this corridor. Splat-Loc provides a robust state estimation module, leveraging the point-cloud representation inherent in GSplat scenes for global pose initialization, in the absence of prior knowledge, and recursive real-time pose localization, given only RGB images. The most compute-intensive procedures in our navigation pipeline, such as the computation of the B\'ezier trajectories and the pose optimization problem run primarily on the CPU, freeing up GPU resources for GPU-intensive tasks, such as online training of Gaussian Splats. We demonstrate the safety and robustness of our pipeline in both simulation and hardware experiments, where we show online re-planning at 5 Hz and pose estimation at about 25 Hz, an order of magnitude faster than Neural Radiance Field (NeRF)-based navigation methods, thereby enabling real-time navigation.

Abstract--We introduce a transformation of a Neural Radiance Field (NeRF) to an equivalent Poisson Point Process (PPP). This PPP transformation allows for rigorous quantification of uncertainty in NeRFs, in particular, for computing collision probabilities for a robot navigating through a NeRF environment. The PPP is a generalization of a probabilistic occupancy grid to the continuous volume and is fundamental to the volumetric ray-tracing model underlying radiance fields. Building upon this PPP representation, we present a chance-constrained trajectory optimization method for safe robot navigation in NeRFs. Our method relies on a voxel representation called the Probabilistic Unsafe Robot Region (PURR) that spatially fuses the chance constraint with the NeRF model to facilitate fast trajectory optimization. We then combine a graph-based search with a spline-based trajectory optimization to yield robot trajectories through the NeRF that are guaranteed to satisfy a user-specific collision probability. We validate our chance constrained planning method through simulations and hardware experiments, showing superior performance compared to prior works on trajectory planning in NeRF environments. Figure 1: (a) Ground-truth of the Stonehenge scene, (b) Poisson Constructing an environment model from onboard sensors, Point Process (PPP) of the scene represented as a point cloud, such as RGB(-D) cameras, lidar, or touch sensors, is a fundamental (c) Probabilistically Unsafe Robot Region (PURR) of scene, challenge for any autonomous system. Radiance Fields (NeRFs) [1] have emerged as a promising 3D scene representation with potential applications in a variety of robotics domains including SLAM [2], pose estimation [3], such as (watertight) triangle meshes [9], occupancy grids [10], [4], reinforcement learning [5], and grasping [6]. NeRFs offer or Signed Distance Fields (SDFs) [11], occupancy is welldefined several potential benefits over traditional scene representations: and simple to query. NeRFs, however, do not admit they can be trained using only monocular RGB images, they simple point-wise occupancy queries, since they represent the provide a continuous representation of obstacle geometry, and scene geometry implicitly through a continuous volumetric they are memory-efficient, especially considering the photorealistic density field.